© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 5059
    Prev
    Next
    INDEX
    Explanations

    Advice/Instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.76
    ImageContext
    -0.66
    ertale
    -0.66
    boer
    -0.64
     autorytatywna
    -0.63
    getWriter
    -0.63
    celotti
    -0.61
     BoxDecoration
    -0.60
    Autoritní
    -0.60
     else
    -0.59
    POSITIVE LOGITS
     betweenstory
    0.60
    fromnode
    0.54
    例句
    0.51
     <=",
    0.44
    amerikanischer
    0.43
    Never
    0.42
     umane
    0.42
     aldrig
    0.41
    contentLoaded
    0.39
     umana
    0.39
    Activations Density 0.017%

    No Known Activations